Skip to main content
Glama
cliwant

mcp-sam-gov

nih_reporter_search_projects

Read-only

Search NIH RePORTER research-grant projects by state, organization, and fiscal year, with pagination. Returns award amounts, PIs, and UEI identifiers for joining to federal spending data.

Instructions

Search awarded NIH RePORTER research-grant projects (keyless; api.reporter.nih.gov v2, POST/JSON), joinable to SAM/USAspending via primary_uei. LIVE-CONFIRMED-narrowing criteria ONLY, AND-combined: orgStates (UPPERCASE 2-letter USPS — lowercase/unknown code silently returns zeros), orgNames (≤512 chars each, ≤20 names), fiscalYears (int array, 1985..currentYear+1, ≤20), limit (1..500), offset (0..14,999). Returns { projects:[{ projectNum, projectTitle, fiscalYear, awardAmount, organization:{name, state, primaryUei, primaryDuns, ueis, duns}, principalInvestigators, contactPiName, fundingIc }] } + honest _meta. HONESTY: records are RESEARCH GRANTS, NOT procurement contracts — primaryUei joins SAM/USAspending but the award nature differs (disclosed in every _meta.notes). totalAvailable = EXACT meta.total (NEVER the page size, NEVER a lower bound). NIH caps keyless retrieval at the first 15,000 records (offset 0..14,999); offset ≥ 15,000 → invalid_input; past the window the count stays exact while records are UNREACHABLE (disclosed in a note). An unscoped query returns the first page + exact total + narrow-your-criteria note. agencyIcCodes is NOT a filter (NIH silently drops it — would be a false 'applied'). awardAmount is number|null (genuine $0 is 0, absent is null). Genuine total:0 → complete:true/total:0; outage/5xx THROWS; 400 (bad offset/limit/type) → invalid_input; 200 not {meta,results} or non-numeric meta.total → schema_drift.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoProjects per page (upstream hard cap 500), 1..500, default 50.
offsetNo0-based offset into the result set. HARD-CAPPED at 14,999: NIH caps keyless retrieval at the first 15,000 records (offset 0..14,999), so offset ≥ 15,000 is refused (invalid_input) — narrow criteria to reach records beyond the window. The count (totalAvailable) stays EXACT past the window.
orgNamesNoRecipient-organization name filter values (each ≤512 chars, max 20). LIVE-CONFIRMED to narrow. e.g. ['MASSACHUSETTS INSTITUTE OF TECHNOLOGY']. A value matching no org returns a genuine total:0.
orgStatesNoRecipient-organization US state/territory 2-letter USPS codes (UPPERCASE — the enum is the SSRF value guard + the silent-zero guard: a lowercase 'ca' or an unknown 'ZZ' silently returns zeros, so a typo is an invalid_input, never read as 'no NIH funding'). LIVE-CONFIRMED to narrow. e.g. ['CA','MA']. Max 20.
fiscalYearsNoNIH fiscal years to include (int array, 1985..2027, max 20). LIVE-CONFIRMED to narrow. e.g. [2023,2024].

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.12.0

TDQS

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnlyHint and openWorldHint annotations, the description discloses many non-obvious behaviors: silent zero returns for lowercase/unknown state codes, NIH's 15,000-record cap, offset ≥15,000 refusal, agencyIcCodes being silently dropped, exact total semantics, error type classification, and schema_drift handling. This is far more than annotations provide and is a model of transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long, but it is well-structured with front-loaded purpose and uppercase markers ('LIVE-CONFIRMED', 'HONESTY'). Every paragraph delivers actionable caveats, and although 'keyless' is repeated twicejam and the prose is dense, the complexity of the NIH API behavior justifies the length.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description provides the complete return shape ({projects:[...]} plus honest _meta), error mapping for 400/5xx/schema_drift, filtering constraints, cap details, and destinction from procurement contracts. An agent has everything needed to call this tool correctly and interpret results.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already documents every parameter richly (100% coverage), so the baseline is 3. The description adds extra behavioral meaning—for example, orgStates values are an 'SSRF value guard + silent-zero guard,' all filters are 'LIVE-CONFIRMED to narrow,' and agencyIcCodes is explicitly called out as a non-filter. That additional context justifies a 4.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Search awarded NIH RePORTER research-grant projects.' It also names the exact API (api.reporter.nih.gov v2, POST/JSON) and keyless access, which distinguishes it from sibling tools like NSF awards or USAspending without ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives strong usage context: it covers NIH research grants, explicitly warns they are 'NOT procurement contracts,' and notes that primary_uei joins SAM/USAspending while the award nature differs. It also advises that unscoped queries return a narrowing notetee. However, it does not explicitly name sibling alternatives, so it stops just short of full routing guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools